Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +1 -1
- README.md +6 -44
- config.json +13 -15
- config_sentence_transformers.json +2 -2
- model.safetensors +2 -2
- modules.json +6 -0
- sentence_bert_config.json +1 -1
- special_tokens_map.json +19 -5
- tokenizer.json +0 -0
- tokenizer_config.json +25 -17
- vocab.txt +5 -0
1_Pooling/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"word_embedding_dimension":
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
|
|
1 |
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
README.md
CHANGED
@@ -5,13 +5,12 @@ tags:
|
|
5 |
- sentence-transformers
|
6 |
- feature-extraction
|
7 |
- sentence-similarity
|
8 |
-
- transformers
|
9 |
|
10 |
---
|
11 |
|
12 |
# HSR-HF/sts-rf-bc-contrastive
|
13 |
|
14 |
-
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a
|
15 |
|
16 |
<!--- Describe your model here -->
|
17 |
|
@@ -36,44 +35,6 @@ print(embeddings)
|
|
36 |
|
37 |
|
38 |
|
39 |
-
## Usage (HuggingFace Transformers)
|
40 |
-
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
|
41 |
-
|
42 |
-
```python
|
43 |
-
from transformers import AutoTokenizer, AutoModel
|
44 |
-
import torch
|
45 |
-
|
46 |
-
|
47 |
-
#Mean Pooling - Take attention mask into account for correct averaging
|
48 |
-
def mean_pooling(model_output, attention_mask):
|
49 |
-
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
50 |
-
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
51 |
-
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
52 |
-
|
53 |
-
|
54 |
-
# Sentences we want sentence embeddings for
|
55 |
-
sentences = ['This is an example sentence', 'Each sentence is converted']
|
56 |
-
|
57 |
-
# Load model from HuggingFace Hub
|
58 |
-
tokenizer = AutoTokenizer.from_pretrained('HSR-HF/sts-rf-bc-contrastive')
|
59 |
-
model = AutoModel.from_pretrained('HSR-HF/sts-rf-bc-contrastive')
|
60 |
-
|
61 |
-
# Tokenize sentences
|
62 |
-
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
63 |
-
|
64 |
-
# Compute token embeddings
|
65 |
-
with torch.no_grad():
|
66 |
-
model_output = model(**encoded_input)
|
67 |
-
|
68 |
-
# Perform pooling. In this case, mean pooling.
|
69 |
-
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
70 |
-
|
71 |
-
print("Sentence embeddings:")
|
72 |
-
print(sentence_embeddings)
|
73 |
-
```
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
## Evaluation Results
|
78 |
|
79 |
<!--- Describe how your model was evaluated -->
|
@@ -86,9 +47,9 @@ The model was trained with the parameters:
|
|
86 |
|
87 |
**DataLoader**:
|
88 |
|
89 |
-
`
|
90 |
```
|
91 |
-
{'batch_size': 8}
|
92 |
```
|
93 |
|
94 |
**Loss**:
|
@@ -120,8 +81,9 @@ Parameters of the fit()-Method:
|
|
120 |
## Full Model Architecture
|
121 |
```
|
122 |
SentenceTransformer(
|
123 |
-
(0): Transformer({'max_seq_length':
|
124 |
-
(1): Pooling({'word_embedding_dimension':
|
|
|
125 |
)
|
126 |
```
|
127 |
|
|
|
5 |
- sentence-transformers
|
6 |
- feature-extraction
|
7 |
- sentence-similarity
|
|
|
8 |
|
9 |
---
|
10 |
|
11 |
# HSR-HF/sts-rf-bc-contrastive
|
12 |
|
13 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
14 |
|
15 |
<!--- Describe your model here -->
|
16 |
|
|
|
35 |
|
36 |
|
37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
## Evaluation Results
|
39 |
|
40 |
<!--- Describe how your model was evaluated -->
|
|
|
47 |
|
48 |
**DataLoader**:
|
49 |
|
50 |
+
`torch.utils.data.dataloader.DataLoader` of length 796 with parameters:
|
51 |
```
|
52 |
+
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
53 |
```
|
54 |
|
55 |
**Loss**:
|
|
|
81 |
## Full Model Architecture
|
82 |
```
|
83 |
SentenceTransformer(
|
84 |
+
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
|
85 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
86 |
+
(2): Normalize()
|
87 |
)
|
88 |
```
|
89 |
|
config.json
CHANGED
@@ -1,26 +1,24 @@
|
|
1 |
{
|
2 |
"_name_or_path": "/content/output_train",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
-
"layer_norm_eps": 1e-
|
15 |
-
"max_position_embeddings":
|
16 |
-
"model_type": "
|
17 |
"num_attention_heads": 12,
|
18 |
-
"num_hidden_layers":
|
19 |
-
"pad_token_id":
|
20 |
-
"
|
21 |
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.40.
|
23 |
-
"
|
24 |
-
"use_cache": true,
|
25 |
-
"vocab_size": 30522
|
26 |
}
|
|
|
1 |
{
|
2 |
"_name_or_path": "/content/output_train",
|
3 |
"architectures": [
|
4 |
+
"MPNetModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.2",
|
23 |
+
"vocab_size": 30527
|
|
|
|
|
24 |
}
|
config_sentence_transformers.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
"sentence_transformers": "2.0.0",
|
4 |
-
"transformers": "4.
|
5 |
-
"pytorch": "1.
|
6 |
},
|
7 |
"prompts": {},
|
8 |
"default_prompt_name": null
|
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.6.1",
|
5 |
+
"pytorch": "1.8.1"
|
6 |
},
|
7 |
"prompts": {},
|
8 |
"default_prompt_name": null
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29be9e4e101225bdda169646851a0c0cc63b5554cb49f223bbf8a7dd104007d1
|
3 |
+
size 437967672
|
modules.json
CHANGED
@@ -10,5 +10,11 @@
|
|
10 |
"name": "1",
|
11 |
"path": "1_Pooling",
|
12 |
"type": "sentence_transformers.models.Pooling"
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
}
|
14 |
]
|
|
|
10 |
"name": "1",
|
11 |
"path": "1_Pooling",
|
12 |
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
}
|
20 |
]
|
sentence_bert_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"max_seq_length":
|
3 |
"do_lower_case": false
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"max_seq_length": 384,
|
3 |
"do_lower_case": false
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -1,27 +1,41 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
"sep_token": {
|
24 |
-
"content": "
|
25 |
"lstrip": false,
|
26 |
"normalized": false,
|
27 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
},
|
37 |
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
"rstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,63 +1,71 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "[
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
-
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
-
"
|
|
|
49 |
"max_length": 128,
|
50 |
"model_max_length": 512,
|
51 |
-
"never_split": null,
|
52 |
"pad_to_multiple_of": null,
|
53 |
-
"pad_token": "
|
54 |
"pad_token_type_id": 0,
|
55 |
"padding_side": "right",
|
56 |
-
"sep_token": "
|
57 |
"stride": 0,
|
58 |
"strip_accents": null,
|
59 |
"tokenize_chinese_chars": true,
|
60 |
-
"tokenizer_class": "
|
61 |
"truncation_side": "right",
|
62 |
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "[UNK]"
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
+
"content": "<s>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"104": {
|
36 |
+
"content": "[UNK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
+
},
|
43 |
+
"30526": {
|
44 |
+
"content": "<mask>",
|
45 |
+
"lstrip": true,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
}
|
51 |
},
|
52 |
+
"bos_token": "<s>",
|
53 |
"clean_up_tokenization_spaces": true,
|
54 |
+
"cls_token": "<s>",
|
|
|
55 |
"do_lower_case": true,
|
56 |
+
"eos_token": "</s>",
|
57 |
+
"mask_token": "<mask>",
|
58 |
"max_length": 128,
|
59 |
"model_max_length": 512,
|
|
|
60 |
"pad_to_multiple_of": null,
|
61 |
+
"pad_token": "<pad>",
|
62 |
"pad_token_type_id": 0,
|
63 |
"padding_side": "right",
|
64 |
+
"sep_token": "</s>",
|
65 |
"stride": 0,
|
66 |
"strip_accents": null,
|
67 |
"tokenize_chinese_chars": true,
|
68 |
+
"tokenizer_class": "MPNetTokenizer",
|
69 |
"truncation_side": "right",
|
70 |
"truncation_strategy": "longest_first",
|
71 |
"unk_token": "[UNK]"
|
vocab.txt
CHANGED
@@ -1,3 +1,7 @@
|
|
|
|
|
|
|
|
|
|
1 |
[PAD]
|
2 |
[unused0]
|
3 |
[unused1]
|
@@ -30520,3 +30524,4 @@ necessitated
|
|
30520 |
##:
|
30521 |
##?
|
30522 |
##~
|
|
|
|
1 |
+
<s>
|
2 |
+
<pad>
|
3 |
+
</s>
|
4 |
+
<unk>
|
5 |
[PAD]
|
6 |
[unused0]
|
7 |
[unused1]
|
|
|
30524 |
##:
|
30525 |
##?
|
30526 |
##~
|
30527 |
+
<mask>
|